A general non-asymptotic framework, which evaluates the performance of any procedure at individual functions, is introduced in the context of estimating convex functions at a point. This framework, which is significantly different from the conventional minimax theory, is also applicable to other problems in shape constrained inference. A benchmark is provided for the mean squared error of any e...

In this paper, a one-layer recurrent neural network is proposed for solving non-smooth convex optimization problems with linear equality constraints. Comparing with the existing neural networks, the proposed neural network has simpler architecture and the number of neurons is the same as that of decision variables in the optimization problems. The global convergence of the neural network can be...

A new nonparametric estimate of a convex regression function is proposed and its stochastic properties are studied. The method starts with an unconstrained estimate of the derivative of the regression function, which is firstly isotonized and then integrated. We prove asymptotic normality of the new estimate and show that it is first order asymptotically equivalent to the initial unconstrained ...

Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the underlying loss function is increasing in the number of incorrect predictions. Ho...

We consider scheduling jobs online to minimize the objective ∑ i∈[n] wig(Ci− ri), where wi is the weight of job i, ri is its release time, Ci is its completion time and g is any non-decreasing convex function. Previously, it was known that the clairvoyant algorithm Highest-DensityFirst (HDF) is (2 + )-speed O(1)-competitive for this objective on a single machine for any fixed 0 < < 1 [21]. We s...

Distributed machine learning allows different parties to learn a single model over all data sets without disclosing their own data. In this paper, we propose weighted distributed differentially private (WD-DP) empirical risk minimization (ERM) method train in setting, considering weights of clients. For the first time, theoretically analyze benefits brought by paradigm learning. Our advances st...

We consider the minimization of a function G defined on R , which is the sum of a (non necessarily convex) differentiable function and a (non necessarily differentiable) convex function. Moreover, we assume that G satisfies the KurdykaLojasiewicz property. Such a problem can be solved with the Forward-Backward algorithm. However, the latter algorithm may suffer from slow convergence. We propose...

We study the interplay between the behaviour of approximately convex (and approximately affine) functions on the unit ball of a Banach space and the geometry of Banach K-spaces. Introduction This paper deals with the local stability of convexity, affinity and Jensen functional equation on infinite dimensional Banach spaces. Recall that a function f : D → R is said to be ε-convex if it satisfies...